Delete observations from memory. Can delete by ID, session, project, type, or date.
AI agents call forget to permanently remove resources in GraphHub — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data (observations) from the GraphHub knowledge graph memory system. Once deleted, these observations cannot be recovered. While the blast radius is somewhat contained to the specific server's session memory rather than persistent external systems, the destructive nature of permanent data deletion warrants the Destructive category, which takes precedence over Write.
From the tool's definition Tool is named 'forget' and description states 'Delete observations from memory' with multiple deletion filters (by ID, session, project, type, or date).
Documented attack patterns abuse exactly the kind of access forget gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GraphHub, and nothing reaches the server without passing your rules. This is the rule we recommend for forget:
{
"version": "1",
"default": "deny",
"hide": [
"forget"
]
} forget disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete observations from memory. Can delete by ID, session, project, type, or date. It is categorised as a Destructive tool in the GraphHub MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GraphHub MCP server in PolicyLayer and add a rule for forget: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches GraphHub. Nothing to install.
forget is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the forget rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for forget. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
forget is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GraphHub, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 GraphHub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.